Apparatus and control method for recommending applications based on context-awareness

Abstract

Disclosed are an apparatus and control method for recommending an application based on a recognized situation of a user of an electronic device by executing an artificial intelligence (AI) algorithm and/or machine learning algorithm in a 5G environment connected for the Internet of Things and a driving method thereof. The apparatus control method according to an embodiment of the present disclosure includes applying context information including at least one of environmental information collected through a sensor of the electronic device or a network, or usage information generated by the use of the electronic device to a machine learning based first learning model in response to a user input, and displaying, on a display, a first shortcut related to an application determined on the basis of a result of applying the context information to the first learning model and displaying, on the display, a second shortcut related to a preset application.

What is claimed is: 
     
       1. A method performed by an electronic device, the method comprising:
 applying context information to a machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through a sensor of the electronic device or a network, or usage information generated by use of the electronic device; 
 displaying, on a display, a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 displaying, on the display, a second shortcut related to a preset application, 
 wherein the method further comprises, before receiving of the user input, 
 receiving a second learning model from a first server device; 
 generating and storing context information; and 
 training the second learning model using training data in which a user selected application or a user selected application function is configured as a label under a condition of the stored context information to generate the first learning model, 
 wherein the method further comprises, before the generating of the first learning model, 
 determining whether the electronic device is connected to a power source; 
 determining whether a user uses the electronic device; 
 comparing an estimated amount of time the user is expected not to use the electronic device with an estimated amount time for generating the first learning model; and 
 determining whether to generate the first learning model based on a result of the comparing of the estimated amount of time. 
 
     
     
       2. The method of  claim 1 , wherein the first learning model is a learning model trained using training data in which a user selected application or a user selected application function is configured as a label under a condition of specific context information. 
     
     
       3. The method of  claim 1 , wherein the usage information comprises at least one of call list information, message information, schedule information, application usage information, network usage information, or internet usage information. 
     
     
       4. The method of  claim 1 , further comprising:
 determining that the electronic device is connected to another device; 
 receiving the user input through a network connected to the another device; and 
 displaying the first shortcut or displaying the second shortcut associated with a type of the another device, on a display of the another device. 
 
     
     
       5. The method of  claim 1 , wherein the context information further comprises at least one of environmental information, which is collected through a sensor of another device or the network, or usage information generated by use of the another device. 
     
     
       6. The method of  claim 1 , wherein the generating and storing of the context information comprises storing at least one of the environmental information or the usage information in association with geographic information or time information. 
     
     
       7. The method of  claim 1 , wherein the displaying of the first shortcut and the second shortcut comprises displaying, on the display, an arrangement of a plurality of first shortcuts and a plurality of second shortcuts to be disposed in respectively different curves. 
     
     
       8. The method of  claim 1 , further comprising: before the displaying of the first shortcut and the displaying of the second shortcut, checking an application running on the electronic device,
 wherein the second shortcut is a shortcut preset to be associated with the running application. 
 
     
     
       9. The method of  claim 8 , wherein the second shortcut is a shortcut to a function provided by the running application or a function provided by another application. 
     
     
       10. A method performed by an electronic device, the method comprising:
 applying context information to a machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through a sensor of the electronic device or a network, or usage information generated by use of the electronic device; 
 displaying, on a display, a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 displaying, on the display, a second shortcut related to a preset application, 
 wherein the method further comprises, before receiving of the user input, 
 receiving a second learning model from a first server device; 
 generating and storing context information; and 
 training the second learning model using training data in which a user selected application or a user selected application function is configured as a label under a condition of the stored context information to generate the first learning model, 
 wherein the method further comprises, after the generating of the first learning model, transmitting information related to a difference between the first learning model and the second learning model to a second server device. 
 
     
     
       11. A method performed by an electronic device, the method comprising:
 applying context information to a machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through a sensor of the electronic device or a network, or usage information generated by use of the electronic device; 
 displaying, on a display, a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 displaying, on the display, a second shortcut related to a preset application, 
 wherein the method further comprises, before receiving of the user input, 
 receiving a second learning model from a first server device; 
 generating and storing context information; and 
 training the second learning model using training data in which a user selected application or a user selected application function is configured as a label under the condition of the stored context information to generate the first learning model, 
 wherein the method further comprises, after the generating of the first learning model, transmitting the first learning model to a second server device and requesting to store the first learning model as associated with the user. 
 
     
     
       12. A method performed by an electronic device, the method comprising:
 applying context information to a machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through a sensor of the electronic device or a network, or usage information generated by use of the electronic device; 
 displaying, on a display, a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 displaying, on the display, a second shortcut related to a preset application, 
 wherein the method further comprises, before receiving of the user input, 
 receiving a second learning model from a first server device; 
 generating and storing context information; and 
 training the second learning model using training data in which a user selected application or a user selected application function is configured as a label under the condition of the stored context information to generate the first learning model, 
 wherein the method further comprises, after the displaying of the first shortcut and the displaying of the second shortcut, 
 monitoring a response of a user to the first shortcut; and 
 based on the response corresponding to a preset reference, re-training the first learning model with training data reflecting additional context information generated or stored after the generating of the first learning model. 
 
     
     
       13. The method of  claim 12 , wherein the monitoring of the response of the user comprises monitoring whether the first shortcut is used by the user or monitoring whether an application not related to the first shortcut is used by the user. 
     
     
       14. A computer program product comprising a non-transitory machine readable medium having a computer readable program stored therein, wherein the computer readable program, when executed by a computing device, causes the computing device to:
 apply context information to a machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through a sensor of the electronic device or a network, or usage information generated by use of the electronic device; 
 display, on a display, a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 display, on the display, a second shortcut related to a preset application, 
 wherein the computer readable program, when executed by the computing device, further causes the computing device to, before receiving of the user input, 
 receive a second learning model from a first server device; 
 generate and store context information; and 
 train the second learning model using training data in which a user selected application or a user selected application function is configured as a label under a condition of the stored context information to generate the first learning model, 
 wherein the computer readable program, when executed by the computing device, further causes the computing device to, before the generating of the first learning model, 
 determine whether the electronic device is connected to a power source; 
 determine whether a user uses the electronic device; 
 compare an estimated amount of time the user is expected not to use the electronic device with an estimated amount time for generating the first learning model; and 
 determine whether to generate the first learning model based on a result of the comparing of the estimated amount of time. 
 
     
     
       15. An electronic device comprising:
 a processor; 
 a memory electrically connected to the processor and configured to store at least one instruction performed in the processor and parameters of a machine learning based first learning model; 
 at least one sensor configured to sense physical information; 
 a display configured to display a user interface, 
 wherein the processor is configured to: 
 apply context information to the machine learning based first learning model in response to a user input, the context information including at least one of environmental information, which is collected through the sensor or a network, or usage information generated by use of the electronic device; 
 cause the display to display a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; and 
 cause the display to display a second shortcut related to a preset application, 
 wherein the processor is further configured to, before receiving of the user input, 
 receive a second learning model from a first server device via the network, 
 train the second learning model using stored context information as training data to generate the first learning model, and 
 transmit information related to a difference between the first learning model and the second learning model to a second server device via the network. 
 
     
     
       16. The electronic device of  claim 15 , wherein the processor is further configured to:
 re-train the first learning model with training data reflecting additional context information generated or stored after generating of the first learning model based on a response of a user to the first shortcut. 
 
     
     
       17. The electronic device of  claim 15 , wherein the processor is further configured to:
 cause the display to display an arrangement of a plurality of first shortcuts and a plurality of second shortcuts to be disposed in respectively different curves. 
 
     
     
       18. The electronic device of  claim 15 , wherein the processor is further configured to:
 check an application running on the electronic device; and 
 cause the display to display a shortcut preset to be associated with the running application as the second shortcut. 
 
     
     
       19. The electronic device of  claim 15 , wherein the processor is further configured to:
 receive additional context information via the network, wherein the additional context information includes at least one of environment information of another device or usage information of the another device. 
 
     
     
       20. An electronic device, comprising:
 a processor; 
 a memory electrically connected to the processor and configured to store at least one instruction performed in the processor and parameters of a machine learning based first learning model; 
 at least one sensor configured to sense physical information; 
 wherein the processor is configured to: 
 apply context information to the machine learning based first learning model in response to a user input received from another device through a network, the context information including at least one of environmental information; 
 cause the another device to display a first shortcut related to an application determined on a basis of a result of applying the context information to the first learning model; 
 cause the another device to display a second shortcut related to a preset application, 
 wherein, the environmental information is collected through the sensor of the electronic device or the network of the electronic device, or usage information generated by use of the electronic device, 
 wherein the another device is connected to the electronic device, uses a function of the electronic device and displays output of the function of the electronic device, 
 wherein the processor is further configured to, before receiving of the user input, 
 receive a second learning model from a first server device; 
 generate and store the context information; and 
 train the second learning model using training data in which a user selected application or a user selected application function is configured as a label under a condition of the stored context information to generate the first learning model, 
 wherein the processor is further configured to, before the generating of the first learning model, 
 determine whether the electronic device is connected to a power source; 
 determine whether a user uses the electronic device; 
 compare an estimated amount of time the user is expected not to use the electronic device with an estimated amount time for generating the first learning model; and 
 determine whether to generate the first learning model based on a result of the comparing of the estimated amount of time. 
 
     
     
       21. The electronic device of  claim 20 , wherein the second shortcut displayed on the another device is associated with an application preset in relation to the another device.